© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96682
    Prev
    Next
    INDEX
    Explanations

    military terminology and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roe
    -0.07
    agrams
    -0.07
    TEE
    -0.07
    cerer
    -0.07
    soever
    -0.07
    zcze
    -0.07
    fy
    -0.06
    olt
    -0.06
    489
    -0.06
    tees
    -0.06
    POSITIVE LOGITS
    à¹īว
    0.06
    éļ
    0.06
    _defaults
    0.06
    wnd
    0.06
    ais
    0.06
    ä¸ĺ
    0.06
    aid
    0.06
     Claudia
    0.06
    <<
    0.06
     hedge
    0.06
    Activations Density 0.013%

    No Known Activations